EP0976054A1 - Address generation and data path arbitration to and from sram to accommodate multiple transmitted packets - Google Patents
Address generation and data path arbitration to and from sram to accommodate multiple transmitted packetsInfo
- Publication number
- EP0976054A1 EP0976054A1 EP97904161A EP97904161A EP0976054A1 EP 0976054 A1 EP0976054 A1 EP 0976054A1 EP 97904161 A EP97904161 A EP 97904161A EP 97904161 A EP97904161 A EP 97904161A EP 0976054 A1 EP0976054 A1 EP 0976054A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- data
- fifo
- controller
- bit
- ethernet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/10—Program control for peripheral devices
- G06F13/12—Program control for peripheral devices using hardware independent of the central processor, e.g. channel or peripheral processor
- G06F13/124—Program control for peripheral devices using hardware independent of the central processor, e.g. channel or peripheral processor where hardware is a sequential transfer control unit, e.g. microprocessor, peripheral processor or state-machine
- G06F13/128—Program control for peripheral devices using hardware independent of the central processor, e.g. channel or peripheral processor where hardware is a sequential transfer control unit, e.g. microprocessor, peripheral processor or state-machine for dedicated transfers to a network
Definitions
- This invention relates generally to a method and device for controlling the transmission of information by a station to and from an ethernet and more particularly, to a method and device for increasing the performance of the transmission of information and even more particularly, to a method and device for converting data from a first bit width to a second bit width, generating addresses for the converted data, and arbitrating access to a data path for read or write access to and from an SRAM buffer.
- a local -area network is a communication system that enables personal computers, work stations, file servers, repeaters, data terminal equipment ("DTE”), and other such information processing equipment located within a limited geographical area such as an office, a building, or a cluster of buildings to electronically transfer information among one another.
- DTE data terminal equipment
- Each piece of information processing equipment in the LAN communicates with other information processing equipment in the LAN by following a fixed protocol (or standard) which defines the network operation.
- the ISO Open Systems Interconnection Basic Reference Model defines a seven-layer model for data communications in a LAN.
- the lowest layer in the model is the physical layer which consists of modules that specify (a) the physical media which interconnects the network nodes and over which data is to be electronically transmitted, (b) the manner in which the network nodes interface to the physical transmission media, (c) the process for transferring data over the physical media, and (d) the protocol of the data stream.
- IEEE Standard 802.3 Carrier Sense Multiple Access with Collision Detection (CSMA/CD) Access Method and Physical Layer Specifications, is one of the most widely used standards for the physical layer. Commonly referred to as Ethernet, IEEE Standard 802.3 deals with transferring data over twisted-pair cables or co-axial cables which are typically more expensive than twisted ⁇ pair cables. The lOBase-T protocol of IEEE Standard 802.3 prescribes a rate of 10 megabits/second ("Mbps") for transferring data over twisted-pair cables.
- Mbps megabits/second
- Figure 1 illustrates how a prior art system 10 with a workstation, personal computer, file server, data terminal equipment, or other such information processing equipment, represented by CPU 12, is connected to an ethernet 22 or other types of data communications equipment represented by the media independent interface 24.
- ethernet controller 14 also commonly known as a Network Interface Controller, is situated between the CPU 12 and the incoming (and outgoing) ethernet 22 lines.
- the ethernet 22 connection consists of two pairs of twisted-pair copper cables, an incoming pair referred to as 10R and an outgoing pair referred to as 10T.
- the ethernet controller 14 is responsible for controlling the transmission of outgoing data to the outgoing pair or cable and the reception of incoming data from the incoming pair or cable.
- the outgoing data is Manchester encoded to reduce electromagnetic inter erence.
- the Manchester encoding causes some portions of the data stream to be pulses at 10 MHz while other portions of the data stream are pulses at 5 MHz.
- the ever growing need to transfer more information faster, accompanied by increases in data processing capability, is necessitating an expansion to data transfer rates considerably higher than the 10 Mbps rate prescribed by the lOBase-T protocol.
- the ethernet controller 14 is responsible for controlling the transmission of data from the CPU 12 to the ethernet 22.
- One of the manor problems confronted by the ethernet controller 14 is that the different memory devices in the various components are of differing sizes. For example, there is a requirement to keep semiconductor devices as small as possible.
- bus sizes as small as possible without degrading performance of the device.
- a 16 bit bus is half the size of a 32 bit bus and if it is possible to provide the same performance with a 16 bit bus as a 32 bit bus it is preferable to design the part with a 16 bit bus.
- the smaller the bus size the less probability for manufacturing defects in the bus.
- the SRAM 16 is a 16 bit memory device
- data bus 20 is a 16 bit data bus
- the PCI BUS 18 is typically a 32 bit bus.
- the SRAM 16 is used as a buffer by ethernet controller 14 to prevent delays from occurring in the transmission of data either to the ethernet 22 to the CPU 12 or from the CPU 12 to the ethernet 22. Such delays could be caused, for example, by high latency in the CPU 12 or by a collision on the ethernet 22 causing a sending station to have to retransmit information that has just been sent.
- BX FIFO 26 responsible for receiving data from CPU 12 via PCI BUS 18, changing the format from 32 bits to 16 bits so that it can be transmitted over the 16 bit data bus 20 to SRAM 16.
- addresses there is a requirement for addresses to be generated by BX FIFO 26 and MR FIFO 32 so that the information can be placed into SRAM 16 and retrieved efficiently by MX FIFO 28 and BR FIFO 30 respectively, which are responsible for changing the format from 16 bits as received from SRAM 16 into a 32 bit format.
- an ethernet controller for controlling the transmission of data between a station and an ethernet.
- the ethernet controller includes four FIFOs with associated logic form managing the transmission of data from the station CPU to a buffer memory, from the buffer memory to the ethernet, from the ethernet to the buffer memory, and from the buffer memory to the station CPU.
- the ethernet controller includes an arbiter which arbitrates which FIFO will have priority for the transmission of data.
- the logic associated with each FIFO converts the b t size of the data from a first bit size to a second bit size, generates addresses for writing or reading to or from the buffer memory.
- the logic also converts a 16 bit address into two 8 bit portions for communication over an 8 bit address bus and also converts the two 8 bit portions to the original 16 bit address.
- the arbiter limits each FIFO to a 32 byte transmission per request and after each 32 byte transmission polls the other FIFOs to determine if there is a pending request for a transmission.
- the arbiter grants requests per an arbitration algorithm.
- Each FIFO has a selected size selected to maximize performance of the ethernet controller.
- Figure 1 shows an overall view of a prior art system with a CPU and an ethernet controller with an ethernet connection and a media independent interface connection.
- Figure 2 shows a system as taught by the present invention.
- Figure 3 shows the ethernet controller in more detail.
- Figure 4 illustrates the arbitration algorithm used by the ethernet controller to arbitrate the sequence of read and write accesses .
- Figure 5 illustrates how the different bit size data is located in differing size memory locations.
- Figure 6 illustrates the method of address generation for writing data to the SRAM buffer memory.
- FIG. 7 illustrates the method of address generation for retrieving data from the SRAM buffer memory.
- DETAILED DESCRIPTION Referring now to Figure 1 there is shown an overview of a prior art system 10 with a CPU 12, and an ethernet controller 14 with connections an ethernet 22 and a media independent interface 24.
- the CPU 12 is connected to the ethernet controller 14 by BUS 17.
- BUS 17 Referring now to Figure 2, there is shown a system 11 as taught by the present invention. In this and subsequent figures like numerals will be used to denote like components.
- a portion of the ethernet controller 14 is shown in Figure 2. It is to be understood that the ethernet controller 14 has many other functions than the functions as taught by the present invention and only those components that are pertinent to the present invention are discussed.
- the function of the illustrated portion of the ethernet controller 14 is to manage the transmission of data to and from the ethernet 22 and/or the media independent interface 24.
- the ethernet controller 14 manages the transmission of data by utilizing SRAM 16 as a buffer to prevent the slowing down of the transmission of data to and from either the CPU 12 or the ethernet 22 or the media independent interface 24.
- SRAM 16 as a buffer to prevent the slowing down of the transmission of data to and from either the CPU 12 or the ethernet 22 or the media independent interface 24.
- the transmission of data can be slowed down, for example, the latency of CPU 12 can be high and the transmission of data from the ethernet 22 could be stopped until CPU 12 is freed from other interrupts.
- the CPU 12 could be attempting to send data via the ethernet 22 and the ethernet 22 could be busy which would cause the data from the CPU 12 to be stopped or held until the ethernet 22 is free.
- the ethernet controller 14 has four FIFOs, each with a selected size to maximize the performance of the ethernet controller 14.
- BX FIFO 26 is a 180 Byte FIFO
- MX FIFO 28 is a 112 Byte FIFO
- BR FIFO 30 is a 160 Byte FIFO
- MR FIFO 32 is a 108 Byte FIFO.
- the BX FIFO 26 and the BR FIFO 30 are on the BUS side of ethernet controller 14 and MX FIFO 28 and MR FIFO 32 are on the MAC (Media Access)
- Each of the FIFOs manages either an input or output function.
- the BX FIFO 26 manages the transmission of data from CPU 12 to SRAM 16.
- MX FIFO 28 manages the transmission of data from SRAM 16 to the ethernet 22 or the media independent interface 24.
- MR FIFO 32 manages the transmission of data from either the ethernet 22 or the media independent interface 24.
- BX FIFO 26 is associated with BX LOGIC 34 which generates addresses for SRAM 16 and prepares 32 bit data from the CPU to be transmitted over the 16 bit data path 20 to SRAM
- MX FIFO 28 is associated with MX LOGIC 36 which generates addresses for the 16 bit data to be retrieved from SRAM 16, reads the 16 bit data in SRAM 16, converts the 16 bit data retrieved from SRAM 16 to 32 bits, and writes the 32 bit data to MX FIFO 28.
- MR FIFO 32 is associated with MR LOGIC 38 which converts data received by MR FIFO 32 from ethernet 22 to a 16 bit size and generates addresses for the 16 bit data which is to be written in SRAM 16, and BR FIFO 30 is associated with BR LOGIC 40 which reads data in SRAM 16 that had been received from ethernet 22, changes the data from 16 bit size to 32 bit size and writes the 32 bit size data in BR FIFO 30 from which it will be sent to the CPU 12.
- SRAM CONTROLLER 42 controls the four FIFOs and in cases of conflict, that is, when more than one FIFO requests the bus to transmit data, the SRAM CONTROLLER 42 arbitrates according to a predetermined algorithm which determines which FIFO will have priority and in which order. The algorithm is discussed below.
- the overall operation of the system shown m Figure 3 is as follows.
- the ethernet controller 14 is responsible for the overall operation of the transmission of data from the CPU 12 to the ethernet 22 and for the transmission of data from the ethernet 22 to the CPU 12.
- one of the major problems with the transmission of data to and from the ethernet 22 is that there are various factors that can affect the efficient transmission of any such data.
- One factor is the different speeds that must be accommodated.
- the PCI BUS 18 operates at a speed of 33 MHz and the ethernet 22 operates at a maximum speed of 25 MHz for the 100 Mbit operation which supports full duplex operation with an mterpacket gap of .96 microseconds.
- ethernet controller 14 One of the major functions of ethernet controller 14 is to manage the transfer of data between the various components in such a way as to minimize any delay in either receiving or transmitting such data. For example, when CPU 12 (not shown) wishes to send data to the ethernet 22 t communicates with, and sends data to BX FIFO 26. BX FIFO 26 requests access to the bus from SRAM CONTROLLER 42 via BX REQUEST LINE 44. When BX LOGIC 34 receives a grant from SRAM CONTROLLER 42 via BX CONTROL LINE 46, BX LOGIC 34 changes the 32 bit size data received from the CPU 12 to 16 bit size data and generates addresses for the SRAM 16 for the storage of the data in 16 bit format.
- BX LOGIC 34 is a state machine which controls the flow of data from BX FIFO 26 to SRAM 16 and will operate once it gets a grant signal from SRAM CONTROLLER 42. Because BX FIFO 26 is 32 bits wide and the data bus 20 is 16 bits wide, it will take BX LOGIC 34 two cycles to write the 16 bit size data to SRAM 16 as it can only write 16 bits on a 16 bit size data bus in each cycle. It has been determined that the transfer of data via BX FIFO 26 is maximized, that is, any delay in the transfer of data via BX FIFO 26 is minimized by having the size of BX FIFO 26 at 180 Bytes. As will be discussed below, SRAM CONTROLLER 42 manages the receiving and transmitting of data through all FIFOs including BX FIFO 26 in accordance with an arbitration algorithm that maximizes the performance of the system 11.
- SRAM 16 The size of SRAM 16 is selectable and in this embodiment has been selected to be 64K Bytes, however, it is expandable to at least 128 Bytes. Therefore, it is necessary to have 16 bits of address to access each memory location.
- the ethernet controller 14 has only 8 bits of address ports to save space and to be more cost effective. For this reason, a 16 bit address must be divided into an upper 8 bit portion and a lower 8 bit portion, transmitted via an 8 bit address bus, and reassembled outside the ethernet controller 14 into a 16 bit address. The details of the address generation and transmission are discussed below in conjunction with Figures 6 & 7.
- the ethernet controller 14 is in constant communication with the ethernet network via MX FIFO 28 and depending upon what type of protocol is used, the system determines when data can be sent via ethernet 22.
- MX FIFO 28 requests access to the data bus 20 via MX REQUEST LINE 47 from SRAM CONTROLLER 42.
- MX CONTROL LINE 48 When access is granted and communicated via MX CONTROL LINE 48 to MX LOGIC 36 the data which has been either temporarily written in SRAM 16 or is in MX FIFO 28, will be or has been converted into the original 32 bit form as received from the CPU 12 by BX FIFO 26, will be transmitted by MX FIFO 28 via ethernet 22.
- MX FIFO 28 is a state machine that controls the flow of data from SRAM 16 to MX FIFO 28 and operates when it gets a grant signal from SRAM CONTROLLER 42.
- the MX FIFO 28 is 32 bits wide and the data bus 20 is 16 bits wide, therefore, after MX LOGIC 36 has read 16 bits of data twice and using logic to assemble them in a double word (32 bits) a write signal is given to MX FIFO 28. This means that a write to MX FIFO 28 is given every alternate cycle and a read from SRAM 16 is done every cycle.
- MX FIFO 28 controls the read from SRAM 16 and the write to MX FIFO 28.
- MR FIFO 32 When MR FIFO 32 senses that there is information from the ethernet to be received, MR FIFO 32 requests access from SRAM CONTROLLER 42 to the data bus 20 via MR REQUEST LINE 50. When SRAM CONTROLLER 42 grants access via MR CONTROL LINE 52 the data received by MR FIFO 32 is converted to 16 bit format by MR LOGIC 38 and sent to SRAM 16 via the 16 bit data bus 20.
- the operation of the MR LOGIC 38 is similar to the operation of the BX LOGIC 34 discussed above.
- BR FIFO 30 When the CPU is ready to receive the data received from the ethernet, BR FIFO 30 requests access from SRAM CONTROLLER 42 to the data bus 20 via BR REQUEST LINE 54. When access is granted, SRAM CONTROLLER 42 communicates to BR LOGIC 40 which reads the data from SRAM 16, converts the data which has been stored in 16 bit data format to a 32 bit data format, and forwards the data to BR FIFO 30, which, in turn, sends the data to the CPU.
- SRAM CONTROLLER 42 communicates to BR LOGIC 40 which reads the data from SRAM 16, converts the data which has been stored in 16 bit data format to a 32 bit data format, and forwards the data to BR FIFO 30, which, in turn, sends the data to the CPU.
- the operation of BR LOGIC 40 is similar to the operation of MX LOGIC 36 discussed above.
- FIG 4 there is shown an arbitration algorithm 56 which indicates in which order SRAM CONTROLLER 42 ( Figure 4) will handle requests for the bus for those cases where there are multiple requests at the same time.
- the SRAM CONTROLLER 42 uses the arbitration scheme shown in Figure 4 to handle requests from all four logic blocks.
- the present invention teaches that there is an optimum number of bytes that should be transferred between components in the ethernet controller 42. It has been determined that this optimum number of bytes is approximately 32. This means, for example, that there should be assembled in BX FIFO 26 32 bytes of data before a request is made by BX FIFO 26 for the bus (the only exception is when the last byte to be transferred is detected to be in BX FIFO 26) . In addition, it has also been determined that 32 bytes is the optimum number of bytes to be transferred from one component to the next. When the limit, in this case 32 bytes, has been reached, the system will pause in either sending or receiving and poll the other functions to determine whether there is other information that needs to be sent or received.
- the system will look first to the receive side, indicated at 60, and grant access first to the MAC side receive, indicated at 62. If there is no request pending at 62, the system will then go to the transmit side, indicated at 64 and if there is a request pending at the bus transmit, indicated at 66, will grant access to bus transmit. If there is no request pending at the bus transmit, the system will back out, go to the receive side 60, and grant access to bus receive, indicated at 68. If there is no request pending at 68, the system will then look to transmit 64 then to MAC transmit, indicated at 70.
- FIG. 5 there is illustrated how the byte sized data is stored in the various components in the system.
- BX FIFO 26 with five bytes of data, DO through D4 stored in the FIFO in locations indicated at 72 and 74.
- 32 bits of STATUS data stored in 8 bit bytes, SO through S3, in locations indicated at 76.
- BX LOGIC 34 reads the 32 bit data from BX FIFO 26 and converts it to a 16 bit size at 80 and puts the 16 bit data onto 16 bit data bus 20.
- the 16 bit data is written into SRAM 16 and is written as shown.
- the first memory location, indicated at 82, is reserved by the system and contains two 8-bit bytes, labeled EOPO and EOPl, which represent information concerning where the end-of-packet is located, that is, in which memory location data byte D4 is located.
- the second memory location, indicated at 84 is also reserved by the system and contains two 8-bit bytes, which read in this example, HEX10 in the upper byte location and HEX00 in the lower byte location.
- the data, DO through D4, is in memory locations indicated at 86, followed by two 16 bit memory locations indicated at 88 and 90 where the four 8 bit bytes of STATUS data (SO-S3) are located. Following the STATUS data information memory locations, are four 8 bit bytes of DESCRIPTOR data (DA0- DA3) located in memory locations indicated at 92 and 94.
- MX FIFO 28 When MX FIFO 28 is granted access to the data bus 20 as described above, the 16 bit data is read from SRAM 16, converted into 32 bit data at 96 and forwarded to MX FIFO 28.
- FIG. 6 there is illustrated the method of address generation when data is being written into the SRAM 16.
- the address generation portion of BX LOGIC 26 is shown within dashed line 98 and the address generation portion of MR LOGIC 38 ( Figure 3) would be the same.
- the method of generating addresses for the SRAM 16 begins with the BX WRITE POINTER 100 pointing at a memory location in which the next packet of information will be written.
- the START PACKET POINTER 102 holds the address of the memory location in SRAM 16 from where BX LOGIC 26 begins writing a packet.
- the starting memory location is written with the memory location of the end- of-packet. Because the 16 bit address must be communicated via an 8 bit address bus the 16 bit address must be divided into two 8 bit portions. In order to generate addresses as the data is written it is necessary to increment the lower 8 bit portion of the address as each byte is being written. The upper 8 bit portion is incremented each time a page has been written, that is, when the lower 8 bits read HEXFF.
- BX WRITE POINTER 100 has an increment lower input 104 which increments BX WRITE POINTER 100 each time a byte is written into SRAM 16 and the increment upper input 106 increments BX WRITE POINTER 100 each time a new page is begun, that is, after the lower address byte reaches the value HEXFF.
- the BX WRITE POINTER 100 then contains the 16 bit address of the memory location into which the byte ust written was written. Because the 16 bit address is communicated over an 8 bit address bus, a MUX 108 reformats the 16 bit address into an upper 8 bit portion and a lower 8 bit portion which is communicated via an 8 bit bus represented at
- SRAM 16 converts the two 8 bit address portions into a 16 bit address, indicated at 116.
- the memory location into which the end-of -packet has been written is written into the starting memory location which has been recorded in START PACKET POINTER 102.
- FIG. 7 there is shown the read address generation portion, indicated within dashed line 124 of MX LOGIC 36 which generates a read address for reading data from SRAM 16.
- a read pointer 126 in a portion of SRAM 16 points to a 16 bit memory location in which the byte just read is located.
- the 16 bit memory location is converted by MUX 128 into two 8 bit portions to be placed on the 8 bit address bus, indicated at 130.
- the two 8 bit address portions are received by MX LOGIC 36 and are reassembled by flip-flop 132 into a 16 bit address, indicated at 134.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Communication Control (AREA)
- Small-Scale Networks (AREA)
Abstract
Description
Claims
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/659,728 US5818844A (en) | 1996-06-06 | 1996-06-06 | Address generation and data path arbitration to and from SRAM to accommodate multiple transmitted packets |
US659728 | 1996-06-06 | ||
PCT/US1997/001634 WO1997046944A1 (en) | 1996-06-06 | 1997-02-04 | Address generation and data path arbitration to and from sram to accommodate multiple transmitted packets |
Publications (2)
Publication Number | Publication Date |
---|---|
EP0976054A1 true EP0976054A1 (en) | 2000-02-02 |
EP0976054B1 EP0976054B1 (en) | 2001-08-29 |
Family
ID=24646577
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP97904161A Expired - Lifetime EP0976054B1 (en) | 1996-06-06 | 1997-02-04 | Address generation and data path arbitration to and from sram to accommodate multiple transmitted packets |
Country Status (6)
Country | Link |
---|---|
US (1) | US5818844A (en) |
EP (1) | EP0976054B1 (en) |
JP (1) | JP3803722B2 (en) |
DE (1) | DE69706443T2 (en) |
TW (1) | TW313732B (en) |
WO (1) | WO1997046944A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017055732A1 (en) * | 2015-10-01 | 2017-04-06 | Upmem | Computer device provided with processing in memory and narrow access ports |
Families Citing this family (48)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6363076B1 (en) * | 1998-01-27 | 2002-03-26 | International Business Machines Corporation | Phantom buffer for interfacing between buses of differing speeds |
US6345345B1 (en) * | 1999-01-26 | 2002-02-05 | Advanced Micro Devices, Inc. | Data communications device and associated method for arbitrating access using dynamically programmable arbitration scheme and limits on data transfers |
US6694417B1 (en) | 2000-04-10 | 2004-02-17 | International Business Machines Corporation | Write pipeline and method of data transfer that sequentially accumulate a plurality of data granules for transfer in association with a single address |
US6791555B1 (en) | 2000-06-23 | 2004-09-14 | Micron Technology, Inc. | Apparatus and method for distributed memory control in a graphics processing system |
US20030101312A1 (en) * | 2001-11-26 | 2003-05-29 | Doan Trung T. | Machine state storage apparatus and method |
US7133972B2 (en) | 2002-06-07 | 2006-11-07 | Micron Technology, Inc. | Memory hub with internal cache and/or memory access prediction |
US7200024B2 (en) | 2002-08-02 | 2007-04-03 | Micron Technology, Inc. | System and method for optically interconnecting memory devices |
US7117316B2 (en) | 2002-08-05 | 2006-10-03 | Micron Technology, Inc. | Memory hub and access method having internal row caching |
US7254331B2 (en) | 2002-08-09 | 2007-08-07 | Micron Technology, Inc. | System and method for multiple bit optical data transmission in memory systems |
US6754117B2 (en) | 2002-08-16 | 2004-06-22 | Micron Technology, Inc. | System and method for self-testing and repair of memory modules |
US7149874B2 (en) | 2002-08-16 | 2006-12-12 | Micron Technology, Inc. | Memory hub bypass circuit and method |
US7836252B2 (en) | 2002-08-29 | 2010-11-16 | Micron Technology, Inc. | System and method for optimizing interconnections of memory devices in a multichip module |
US6820181B2 (en) | 2002-08-29 | 2004-11-16 | Micron Technology, Inc. | Method and system for controlling memory accesses to memory modules having a memory hub architecture |
US7102907B2 (en) | 2002-09-09 | 2006-09-05 | Micron Technology, Inc. | Wavelength division multiplexed memory module, memory system and method |
US7003638B2 (en) * | 2002-12-11 | 2006-02-21 | Standard Microsystems Corporation | Memory bus interface for use in a peripheral device |
US7245145B2 (en) | 2003-06-11 | 2007-07-17 | Micron Technology, Inc. | Memory module and method having improved signal routing topology |
US7120727B2 (en) | 2003-06-19 | 2006-10-10 | Micron Technology, Inc. | Reconfigurable memory module and method |
US7428644B2 (en) | 2003-06-20 | 2008-09-23 | Micron Technology, Inc. | System and method for selective memory module power management |
US7260685B2 (en) | 2003-06-20 | 2007-08-21 | Micron Technology, Inc. | Memory hub and access method having internal prefetch buffers |
US7107415B2 (en) | 2003-06-20 | 2006-09-12 | Micron Technology, Inc. | Posted write buffers and methods of posting write requests in memory modules |
US7389364B2 (en) | 2003-07-22 | 2008-06-17 | Micron Technology, Inc. | Apparatus and method for direct memory access in a hub-based memory system |
US7210059B2 (en) | 2003-08-19 | 2007-04-24 | Micron Technology, Inc. | System and method for on-board diagnostics of memory modules |
US7133991B2 (en) | 2003-08-20 | 2006-11-07 | Micron Technology, Inc. | Method and system for capturing and bypassing memory transactions in a hub-based memory system |
US20050050237A1 (en) * | 2003-08-28 | 2005-03-03 | Jeddeloh Joseph M. | Memory module and method having on-board data search capabilities and processor-based system using such memory modules |
US7136958B2 (en) | 2003-08-28 | 2006-11-14 | Micron Technology, Inc. | Multiple processor system and method including multiple memory hub modules |
US7310752B2 (en) | 2003-09-12 | 2007-12-18 | Micron Technology, Inc. | System and method for on-board timing margin testing of memory modules |
US7194593B2 (en) * | 2003-09-18 | 2007-03-20 | Micron Technology, Inc. | Memory hub with integrated non-volatile memory |
US7120743B2 (en) | 2003-10-20 | 2006-10-10 | Micron Technology, Inc. | Arbitration system and method for memory responses in a hub-based memory system |
US7216196B2 (en) * | 2003-12-29 | 2007-05-08 | Micron Technology, Inc. | Memory hub and method for memory system performance monitoring |
US7330992B2 (en) | 2003-12-29 | 2008-02-12 | Micron Technology, Inc. | System and method for read synchronization of memory modules |
US7188219B2 (en) | 2004-01-30 | 2007-03-06 | Micron Technology, Inc. | Buffer control system and method for a memory system having outstanding read and write request buffers |
US7788451B2 (en) | 2004-02-05 | 2010-08-31 | Micron Technology, Inc. | Apparatus and method for data bypass for a bi-directional data bus in a hub-based memory sub-system |
US7181584B2 (en) | 2004-02-05 | 2007-02-20 | Micron Technology, Inc. | Dynamic command and/or address mirroring system and method for memory modules |
US7412574B2 (en) * | 2004-02-05 | 2008-08-12 | Micron Technology, Inc. | System and method for arbitration of memory responses in a hub-based memory system |
US7366864B2 (en) | 2004-03-08 | 2008-04-29 | Micron Technology, Inc. | Memory hub architecture having programmable lane widths |
US7257683B2 (en) | 2004-03-24 | 2007-08-14 | Micron Technology, Inc. | Memory arbitration system and method having an arbitration packet protocol |
US7120723B2 (en) | 2004-03-25 | 2006-10-10 | Micron Technology, Inc. | System and method for memory hub-based expansion bus |
US7447240B2 (en) | 2004-03-29 | 2008-11-04 | Micron Technology, Inc. | Method and system for synchronizing communications links in a hub-based memory system |
US7213082B2 (en) | 2004-03-29 | 2007-05-01 | Micron Technology, Inc. | Memory hub and method for providing memory sequencing hints |
US6980042B2 (en) | 2004-04-05 | 2005-12-27 | Micron Technology, Inc. | Delay line synchronizer apparatus and method |
US7590797B2 (en) | 2004-04-08 | 2009-09-15 | Micron Technology, Inc. | System and method for optimizing interconnections of components in a multichip memory module |
US7162567B2 (en) | 2004-05-14 | 2007-01-09 | Micron Technology, Inc. | Memory hub and method for memory sequencing |
US7222213B2 (en) | 2004-05-17 | 2007-05-22 | Micron Technology, Inc. | System and method for communicating the synchronization status of memory modules during initialization of the memory modules |
US7363419B2 (en) | 2004-05-28 | 2008-04-22 | Micron Technology, Inc. | Method and system for terminating write commands in a hub-based memory system |
US7519788B2 (en) | 2004-06-04 | 2009-04-14 | Micron Technology, Inc. | System and method for an asynchronous data buffer having buffer write and read pointers |
US7310748B2 (en) | 2004-06-04 | 2007-12-18 | Micron Technology, Inc. | Memory hub tester interface and method for use thereof |
US7392331B2 (en) | 2004-08-31 | 2008-06-24 | Micron Technology, Inc. | System and method for transmitting data packets in a computer system having a memory hub architecture |
US8190796B2 (en) * | 2004-11-02 | 2012-05-29 | Standard Microsystems Corporation | Hardware supported peripheral component memory alignment method |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0150084B1 (en) * | 1984-01-03 | 1991-05-29 | Texas Instruments Incorporated | Architecture for intelligent control of data communication adapters |
US5058110A (en) * | 1989-05-03 | 1991-10-15 | Ultra Network Technologies | Protocol processor |
US5119374A (en) * | 1990-05-29 | 1992-06-02 | Advanced Micro Devices, Inc. | Method of and system for implementing multiple levels of asynchronous priority in FDDI networks |
US5313582A (en) * | 1991-04-30 | 1994-05-17 | Standard Microsystems Corporation | Method and apparatus for buffering data within stations of a communication network |
US5434976A (en) * | 1992-09-28 | 1995-07-18 | Standard Microsystems Corporation | Communications controller utilizing an external buffer memory with plural channels between a host and network interface operating independently for transferring packets between protocol layers |
JPH08180006A (en) * | 1994-12-22 | 1996-07-12 | Hitachi Ltd | Network interface and computer network system |
US5729681A (en) * | 1995-10-10 | 1998-03-17 | Intel Corporation | Method of communicating data from a host to a network controller |
-
1996
- 1996-06-06 US US08/659,728 patent/US5818844A/en not_active Expired - Lifetime
- 1996-10-15 TW TW085112541A patent/TW313732B/en active
-
1997
- 1997-02-04 WO PCT/US1997/001634 patent/WO1997046944A1/en active IP Right Grant
- 1997-02-04 EP EP97904161A patent/EP0976054B1/en not_active Expired - Lifetime
- 1997-02-04 DE DE69706443T patent/DE69706443T2/en not_active Expired - Lifetime
- 1997-02-04 JP JP50054098A patent/JP3803722B2/en not_active Expired - Fee Related
Non-Patent Citations (1)
Title |
---|
See references of WO9746944A1 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017055732A1 (en) * | 2015-10-01 | 2017-04-06 | Upmem | Computer device provided with processing in memory and narrow access ports |
FR3042050A1 (en) * | 2015-10-01 | 2017-04-07 | Upmem | |
US20180260161A1 (en) * | 2015-10-01 | 2018-09-13 | Upmem | Computing device with in memory processing and narrow data ports |
US10884657B2 (en) | 2015-10-01 | 2021-01-05 | Upmem | Computing device within memory processing and narrow data ports |
Also Published As
Publication number | Publication date |
---|---|
WO1997046944A1 (en) | 1997-12-11 |
JP2000511726A (en) | 2000-09-05 |
DE69706443D1 (en) | 2001-10-04 |
JP3803722B2 (en) | 2006-08-02 |
DE69706443T2 (en) | 2002-06-13 |
EP0976054B1 (en) | 2001-08-29 |
TW313732B (en) | 1997-08-21 |
US5818844A (en) | 1998-10-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0976054B1 (en) | Address generation and data path arbitration to and from sram to accommodate multiple transmitted packets | |
US5878028A (en) | Data structure to support multiple transmit packets for high performance | |
EP0617368B1 (en) | Arbitration process for controlling data flow through an I/O controller | |
US5247626A (en) | Fddi controller having flexible buffer management | |
EP0459752B1 (en) | Network adapter using buffers and multiple descriptor rings | |
US5933413A (en) | Adaptive priority determination for servicing transmit and receive in network controllers | |
US5444692A (en) | Token star bridge | |
US4593281A (en) | Local area network interframe delay controller | |
JPH04233055A (en) | Server architecture for terminal apparatus | |
US6724769B1 (en) | Apparatus and method for simultaneously accessing multiple network switch buffers for storage of data units of data frames | |
US6084878A (en) | External rules checker interface | |
US5811995A (en) | Circuit for switching between different frequency clock domains that are out of phase | |
US6771654B1 (en) | Apparatus and method for sharing memory using a single ring data bus connection configuration | |
US6741589B1 (en) | Apparatus and method for storing data segments in a multiple network switch system using a memory pool | |
US6574231B1 (en) | Method and apparatus for queuing data frames in a network switch port | |
US6195334B1 (en) | Apparatus and method for terminating a data transfer in a network switch in response to a detected collision | |
GB2301996A (en) | Intermodular communications using system bus controllers | |
US6256313B1 (en) | Triplet architecture in a multi-port bridge for a local area network | |
US5819113A (en) | Method of identifying end of pocket by writing the address of last data into the first location of the memory | |
KR100474658B1 (en) | Address generation and data path arbitration to and from sram to accommodate multiple transmitted packets | |
US6760338B1 (en) | Apparatus and method for monitoring data frames by a shared switching logic during simultaneous accessing of multiple network switch buffers | |
US7143185B1 (en) | Method and apparatus for accessing external memories | |
US6996120B2 (en) | Methods for improving bus performance and bandwidth utilization of a parallel bus LAN | |
JP2001257686A (en) | Computer system and its data communication method | |
Protogeros et al. | Traffic analyser and generator Part 1: High-speed traffic capture for IEEE 802.3/Ethernet networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 19980921 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): DE FR GB |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
17Q | First examination report despatched |
Effective date: 20010208 |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): DE FR GB |
|
REF | Corresponds to: |
Ref document number: 69706443 Country of ref document: DE Date of ref document: 20011004 |
|
ET | Fr: translation filed | ||
REG | Reference to a national code |
Ref country code: GB Ref legal event code: IF02 |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
26N | No opposition filed | ||
REG | Reference to a national code |
Ref country code: GB Ref legal event code: 732E Free format text: REGISTERED BETWEEN 20091210 AND 20091216 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: TP |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20110228 Year of fee payment: 15 Ref country code: FR Payment date: 20110201 Year of fee payment: 15 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 20110124 Year of fee payment: 15 |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20120204 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST Effective date: 20121031 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 69706443 Country of ref document: DE Effective date: 20120901 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20120204 Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20120229 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20120901 |